On the Efficiency of Population-Based Optimization in Finding Best Parameters for RGB-D Visual Odometry

Abstract

Visual odometry es mates the transforma ons between consecu ve frames of a video stream in order to recover the camera's trajectory. As this approach does not require to build a map of the observed environment, it is fast and simple to implement. In the last decade RGB-D cameras proliferated in robo cs, being also the sensors of choice for many prac cal visual odometry systems. Although RGB-D cameras provide readily available depth images, that greatly simplify the frame-to-frame transforma ons computa on, the number of numerical parameters that have to be set properly in a visual odometry system to obtain an accurate trajectory es mate remains high. Whereas se ng them by hand is certainly possible, it is a tedious try-and-error task. Therefore, in this ar cle we make an assessment of two popula on-based approaches to parameter op miza on, that are for long me applied in various areas of robo cs, as means to find best parameters of a simple RGB-D visual odometry system. The op miza on algorithms inves gated here are parcle swarm op miza on and an evolu onary algorithm variant. We focus on the op miza on methods themselves, rather than on the visual odometry algorithm, seeking an efficient procedure to find parameters that minimize the es mated trajectory errors. From the experimental results we draw conclusions as to both the efficiency of the op miza on methods, and the role of parcular parameters in the visual odometry system.

Application of Odometry and Dijkstra Algorithm as Navigation and Shortest Path Determination System of Warehouse Mobile Robot

“…Odometry is used to estimate position coordinates relative to the initial position [26] [27]. The odometry system requires a rotary encoder sensor to detect the number of wheel rotations [28] [29]. Area mapping using the odometry method is to estimate changes in the robot's position over time in a Cartesian diagram [30] [31].…”